Implement ACTIVITY-WP-0021 production automation reliability
All checks were successful
CI Smoke / host-smoke (push) Successful in 0s
CI Smoke / container-smoke (push) Successful in 2s
Build and Publish Container Image / build-and-push (push) Successful in 47s

Root-cause IssueSink 503 (dead Forgejo PAT on issue-core), add state-hub
task sink path B, log runs before emit, harden sync_schedules, deterministic
SBOM/triage reports, DB probe thrash fix, and prod automation-status helper.
This commit is contained in:
tegwick 2026-07-21 04:21:55 +02:00
parent 1209ff6973
commit 98e8aa83bd
15 changed files with 638 additions and 63 deletions

View file

@ -79,7 +79,18 @@ class IssueCoreRestSink(IssueSink):
headers=self._auth_headers(),
timeout=10.0,
)
resp.raise_for_status()
status = getattr(resp, "status_code", None)
if status is not None and status >= 400:
# Surface issue-core backend detail (e.g. dead Gitea token → 503)
# so Temporal history and operator status are actionable.
detail = (getattr(resp, "text", None) or "")[:500]
raise RuntimeError(
f"IssueCoreRestSink POST {self._base_url}/issues/ "
f"failed HTTP {status}: {detail}"
)
if status is None:
# Test doubles may only implement raise_for_status/json.
resp.raise_for_status()
data = resp.json()
return TaskRef(
external_id=data["issue_id"],
@ -97,9 +108,85 @@ class NullSink(IssueSink):
return TaskRef(external_id=synthetic_id, backend="null")
class StateHubProgressSink(IssueSink):
"""Record each TaskSpec as a State Hub progress event (no Forgejo issues).
ACTIVITY-WP-0021 path B: when issue-coreForgejo is unavailable or policy
forbids automated Forgejo issues, operators can set ISSUE_SINK_TYPE=state-hub
so scheduled definitions still complete with observable evidence.
Posts event_type=activity_task_spawn (override with STATE_HUB_TASK_EVENT_TYPE).
"""
def __init__(
self,
base_url: str | None = None,
*,
event_type: str | None = None,
author: str = "activity-core",
timeout_seconds: float = 10.0,
) -> None:
self._base_url = (
base_url
or os.environ.get("STATE_HUB_URL")
or "http://127.0.0.1:8000"
).rstrip("/")
self._event_type = event_type or os.environ.get(
"STATE_HUB_TASK_EVENT_TYPE", "activity_task_spawn"
)
self._author = author
self._timeout = timeout_seconds
def emit(self, task_spec: TaskSpec) -> TaskRef:
from activity_core.state_hub_write import parse_state_hub_write_response
external_id = f"sh-{uuid.uuid4()}"
body = {
"event_type": self._event_type,
"author": self._author,
"summary": task_spec.title[:240] or "activity-core task spawn",
"detail": {
"task_ref": external_id,
"title": task_spec.title,
"description": task_spec.description,
"target_repo": task_spec.target_repo,
"priority": task_spec.priority,
"labels": task_spec.labels,
"source_type": task_spec.source_type,
"source_id": task_spec.source_id,
"triggering_event_id": (
str(task_spec.triggering_event_id)
if task_spec.triggering_event_id is not None
else None
),
"activity_definition_id": task_spec.activity_definition_id,
"backend": "state-hub-progress",
},
}
resp = httpx.post(
f"{self._base_url}/progress/",
json=body,
timeout=self._timeout,
)
if resp.status_code >= 400:
raise RuntimeError(
f"StateHubProgressSink POST {self._base_url}/progress/ "
f"failed HTTP {resp.status_code}: {resp.text[:500]}"
)
data = parse_state_hub_write_response(resp)
progress_id = data.get("id") or data.get("outbox_id") or external_id
return TaskRef(
external_id=str(progress_id),
backend_url=f"{self._base_url}/progress/",
backend="state-hub-progress",
)
def get_issue_sink() -> IssueSink:
"""Factory: returns the configured IssueSink based on ISSUE_SINK_TYPE."""
sink_type = ISSUE_SINK_TYPE.lower()
if sink_type == "null":
return NullSink()
if sink_type in {"state-hub", "state_hub", "progress"}:
return StateHubProgressSink()
return IssueCoreRestSink()